Prerequisites
- A Telnyx account with an API key
- Python 3.9 or higher with
websockets14+ (pip install websockets) for the streaming example
Voices
Telnyx exposes a curated shortlist of voices from the Fish Audio Voice Library rather than accepting arbitrary voice IDs. Voices use the formatFishAudio.<Model>.<VoiceId>, where the model is s2.1-pro (latest, default), s2-pro, or s1:
[happy] or [whispering] — see emotion control for the full syntax.
See the Telnyx Fish Audio provider page for the current voice roster, supported audio formats, and sample rates.
WebSocket streaming
Stream text in and receive base64-encoded audio chunks in real time:voice_settings; without it, audio is delivered as raw PCM at 24 kHz.
REST API
Synthesize a complete utterance with a single HTTP request:output_type to base64_output or audio_id for JSON responses instead.

